I Pointed Chrome's Prompt API at a 1.25 Million Character Memoir, and It Got Interesting Fast
A developer experimented with Chrome's Prompt API using a 1.25 million character memoir to explore its capabilities. The project, called Gemini Nano Book Lab, aims to understand how long texts affect language model performance. The findings highlight various challenges and considerations when using on-device models for extensive inputs.
- ▪The experiment utilized Richard Wagner's memoir, which contains over 1.25 million characters.
- ▪The Chrome extension allows users to interact with the Prompt API locally without cloud dependency.
- ▪Key areas of exploration include model behavior, retrieval costs, and context usage.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 1001514) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Shrijith Venkatramana Posted on May 29 I Pointed Chrome's Prompt API at a 1.25 Million Character Memoir, and It Got Interesting Fast #ai #webdev #programming #productivity Hello, I'm Shrijith Venkatramana. I'm building git-lrc, an AI code reviewer that runs on every commit. Star Us to help devs discover the project. Do give it a try and share your feedback for improving the product.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
